# A simplified version of the bivariate probit model estimated
# by William Greene in his working paper "Marginal Effects in the 
# Bivariate Probit Model" (EC-96-11, June 1996)
#
# The dependent variable in the first equation is equal to 1 if the
# respondent has had any major derogatory credit reports, otherwise
# 0; and in the second equation the dependent variable is 1 if the
# respondent's application for a credit card was accepted, otherwise
# 0. 
#
# The estimates show a strong negative correlation of the disturbance
# across the two equations, which makes sense: unobserved factors
# making a derogatory report more likely also make a successful
# credit-card application less likely.

open greene25_1.gdt
# regressors for first equation
list x1 = const age avgexp
# regressors for second equation
list x2 = const age income ownrent selfempl
biprobit anydrg cardhldr x1 ; x2